---
tags:
- generated_from_trainer
model-index:
- name: small-mlm-wikitext-from-scratch-custom-tokenizer
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# small-mlm-wikitext-from-scratch-custom-tokenizer

This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 7.4613

## Model description

More information needed

## Intended uses & limitations

More information needed

## Training and evaluation data

More information needed

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 3e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- training_steps: 5000

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 8.2616        | 0.4   | 500  | 8.0137          |
| 7.6832        | 0.8   | 1000 | 7.8660          |
| 7.586         | 1.2   | 1500 | nan             |
| 7.4953        | 1.6   | 2000 | 7.6839          |
| 7.4399        | 2.0   | 2500 | 7.6496          |
| 7.3358        | 2.4   | 3000 | 7.5908          |
| 7.3526        | 2.8   | 3500 | 7.5918          |
| 7.2773        | 3.2   | 4000 | nan             |
| 7.2433        | 3.6   | 4500 | 7.4326          |
| 7.2167        | 4.0   | 5000 | 7.4613          |


### Framework versions

- Transformers 4.26.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2